New Paper: A machine learning framework to classify Southeast Asian echolocating bats

The publications keep coming! Tigga and Joe are co-authors on “A machine learning framework to classify Southeast Asian echolocating bats” that just came out in Ecological Indicators. This paper has all you can ask for, if what you’re asking for is using machine learning to classify bat calls in Southeast Asia. Field rats take note: “Our framework allows users to rapidly filter acoustic files for common species and isolate files of interest, cutting the total volume of data to be processed by 86%.” Not only a time saver, but this increases the capacity of researchers to use non-invasive sampling in regions without species-specific call records and can detect species that are often missed when employing other sampling methods.

The four call types used in the Borneo bat classifier and representation of bat ensembles in Borneo, their corresponding call types, and species/sonotypes used to train the bat call classifier.

Ten New Bat Records from Nigeria!

Iroro, Ben, and Tigga recently published ten new species-level bat records from Afi Mountain Wildlife Sanctuary and Cross River National Park in southeastern Nigeria. These new records are especially exciting because Nigeria is both under-sampled and a biodiversity hotspot! Check out the full publication “Hidden Afrotropical Bat Diversity in Nigeria: Ten New Country Records from a Biodiversity Hotspot

Left: Portraits of 34 bats captured during the field survey at Afi Mountain Wildlife Sanctuary and Cross River National Park. M. torquata (e), R. hillorum (j), H. curtus (n), M. inflatus (x), G. cf. humeralis (aa), G. egeria (cc), K. cuprosa (dd), K. phalaena (ff), and N. eisentrauti (hh) are all new country records.

ChiroVox online public call library and accompanying PeerJ publication are live!

ChiroVox, the home of bat recordings from all over the world!

Tigga, along with Former lab members Joe Chun-Chia Huang and Juliana Senawi, recently co-authored “ChiroVox: a public library of bat calls” in PeerJ. The paper was timed to coincide with the launch of online bat call library. The library contains calls from across three cotenants and welcomes quality call contributions to help grow this valuable community resource.